[CPU] Add fused GDN support for AMX CPU platform (#42707)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
@@ -213,9 +213,6 @@ class UnquantizedLinearMethod(LinearMethodBase):
|
||||
|
||||
def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
|
||||
if current_platform.is_cpu():
|
||||
if layer.weight.ndim != 2:
|
||||
# this is not a linear layer
|
||||
return
|
||||
from vllm.model_executor.layers.utils import dispatch_cpu_unquantized_gemm
|
||||
|
||||
dispatch_cpu_unquantized_gemm(layer, remove_weight=True)
|
||||
|
||||
Reference in New Issue
Block a user